No abstract

In chemical and manufacturing processes, unit failures due to equipment degradation can lead to process downtime and significant costs. In this context, finding an optimal maintenance strategy to ensure good unit health while avoiding excessive expensive maintenance activities is highly relevant. We propose a practical approach for the integrated optimization of production and maintenance capable of incorporating uncertain sensor data regarding equipment degradation. To this end, we integrate data-driven stochastic degradation models from Condition-based Maintenance into a process level mixed-integer optimization problem using Robust Optimization. We reduce computational expense by utilizing both analytical and data-based approximations and optimize the Robust Optimization parameters using Bayesian Optimization. We apply our framework to five instances of the State-Task-Network and demonstrate that it can efficiently compromise between equipment availability and cost of maintenance.

This paper presents a method to detect transient disturbances in a multivariate context, and an extension of that method to handle multi-rate systems. Both methods are based on a time series analysis technique known as nearest neighbors, and on multivariate statistics implemented as a singular value decomposition. The motivation for these developments is that there is an increasing industrial requirement for the analysis of data sets comprising measurements from industrial processes together with their associated electrical and mechanical equipment. These systems are increasingly affected by transient disturbances, and their measurements are commonly sampled at different rates. The paper demonstrates superior results with the multivariate method in comparison to the univariate approach, and with the multi-rate method in comparison to a uni-rate method, for which the fast-sampled measurements had to be downsampled. The method is demonstrated on experimental and industrial case studies.

Abstract-Model predictive control (MPC) is investigated as a control method which may offer advantages in frequency control of power systems than the control methods applied today, especially in presence of increased renewable energy penetration. The MPC includes constraints on both generation amount and generation rate of change, and it is tested on a one-area system. The proposed MPC is tested against a conventional proportionalintegral (PI) controller, and simulations show that the MPC improves frequency deviation and control performance.

Optimization problems with uncertain black-box constraints, modeled by warped Gaussian processes, have recently been considered in the Bayesian optimization setting. This work considers optimization problems with aggregated black-box constraints. Each aggregated black-box constraint sums several draws from the same black-box function with different decision variables as arguments in each individual black-box term. Such constraints are important in applications where, e.g., safety-critical measures are aggregated over multiple time periods. Our approach, which uses robust optimization, reformulates these uncertain constraints into deterministic constraints guaranteed to be satisfied with a specified probability, i.e., deterministic approximations to a chance constraint. While robust optimization typically considers parametric uncertainty, our approach considers uncertain functions modeled by warped Gaussian processes. We analyze convexity conditions and propose a custom global optimization strategy for non-convex cases. A case study derived from production planning and an industrially relevant example from oil well drilling show that the approach effectively mitigates uncertainty in the learned curves. For the drill scheduling example, we develop a custom strategy for globally optimizing integer decisions.